PERSUASIONTRACE introduces a Bayesian-network simulated target for multi-turn persuasion that matches human belief dynamics (81 vs 80) better than LLM baselines (64) and enables process-level evaluation.
Training llms for honesty via confessions
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 9roles
method 1polarities
use method 1representative citing papers
Autoregressive transformers exhibit measurable cognitive fatigue during extended generation, quantified by the Fatigue Index that predicts degradation (AUROC 0.95) and repetition (rho 0.94).
Regenerating model responses on de-identified production conversation prefixes yields pre-deployment misbehavior rate forecasts that track realized production rates within 2-5x and outperform adversarial-prompt baselines.
Fixed counterfactual explanation datasets train LMs such that generated explanations track the model's evolving behavior rather than the fixed targets, due to persistent correlation during training.
Reinforcement learning on beneficial traits in realistic domains yields broad improvements on over 80% of out-of-distribution alignment benchmarks and greater resistance to adversarial steering.
LLMs need metacognition to align expressed uncertainty with their actual knowledge boundaries, moving beyond knowledge expansion to reduce confident errors.
Fine-tuning LLMs on narrow misaligned data produces either coherent-persona models where harmful outputs match self-reported misalignment or inverted-persona models where harmful outputs occur alongside claims of alignment.
The paper introduces the Proxy Compression Hypothesis as a unifying framework explaining reward hacking in RLHF as an emergent result of compressing high-dimensional human objectives into proxy reward signals under optimization pressure.
Proxy RL produces a staged proxy-internalization capability that emerges before and predicts reward hacking in coding environments.
citing papers explorer
-
A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing
PERSUASIONTRACE introduces a Bayesian-network simulated target for multi-turn persuasion that matches human belief dynamics (81 vs 80) better than LLM baselines (64) and enables process-level evaluation.
-
Cognitive Fatigue in Autoregressive Transformers: Formalization and Measurement
Autoregressive transformers exhibit measurable cognitive fatigue during extended generation, quantified by the Fatigue Index that predicts degradation (AUROC 0.95) and repetition (rho 0.94).
-
Predicting LLM Safety Before Release by Simulating Deployment
Regenerating model responses on de-identified production conversation prefixes yields pre-deployment misbehavior rate forecasts that track realized production rates within 2-5x and outperform adversarial-prompt baselines.
-
Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision
Fixed counterfactual explanation datasets train LMs such that generated explanations track the model's evolving behavior rather than the fixed targets, due to persistent correlation during training.
-
Reinforcement Learning Towards Broadly and Persistently Beneficial Models
Reinforcement learning on beneficial traits in realistic domains yields broad improvements on over 80% of out-of-distribution alignment benchmarks and greater resistance to adversarial steering.
-
Hallucinations Undermine Trust; Metacognition is a Way Forward
LLMs need metacognition to align expressed uncertainty with their actual knowledge boundaries, moving beyond knowledge expansion to reduce confident errors.
-
Characterizing the Consistency of the Emergent Misalignment Persona
Fine-tuning LLMs on narrow misaligned data produces either coherent-persona models where harmful outputs match self-reported misalignment or inverted-persona models where harmful outputs occur alongside claims of alignment.
-
Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges
The paper introduces the Proxy Compression Hypothesis as a unifying framework explaining reward hacking in RLHF as an emergent result of compressing high-dimensional human objectives into proxy reward signals under optimization pressure.
-
Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization
Proxy RL produces a staged proxy-internalization capability that emerges before and predicts reward hacking in coding environments.